© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74130
    Prev
    Next
    INDEX
    Explanations

    providingfoundentitledantiquequick

    np_acts-logits-general · gemini-2.5-flash-lite

    business scams and deceit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     હતી
    0.46
     앱
    0.43
    ﻂ
    0.43
    ebook
    0.42
    ersiz
    0.42
    Medicine
    0.42
    기를
    0.41
     квіт
    0.41
    otropin
    0.41
     днем
    0.41
    POSITIVE LOGITS
    非法
    0.48
     illegal
    0.47
     priceless
    0.45
     hiding
    0.45
    伪
    0.44
     Another
    0.44
     Constants
    0.44
     Stopped
    0.44
     indestructible
    0.44
     frauds
    0.43
    Activations Density 0.001%

    No Known Activations